Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nc
    -0.08
    谌
    -0.07
     really
    -0.07
    諾
    -0.07
    と言
    -0.07
     announcing
    -0.07
     stunt
    -0.07
     reliant
    -0.07
     anc
    -0.06
    高职
    -0.06
    POSITIVE LOGITS
     Daddy
    0.07
    .gallery
    0.07
     decimal
    0.07
    ://
    0.07
    溦
    0.07
     HDF
    0.07
    _LINES
    0.06
     [...]↵↵
    0.06
    ......↵↵
    0.06
     Kapoor
    0.06
    Act Density 0.000%

    No Known Activations